A vehicle-road collaboration method, system, terminal and storage medium

The vehicle image determines the truck weight measurement status at the entrance of the highway, which solves the problem of weight inaccurate caused by the pound jump operation, realizes accurate management of vehicles and cargo, and reduces the occurrence of traffic accidents.

CN118587904BActive Publication Date: 2024-12-03SHIYUAN (SHANGHAI) TRANSPORTATION TECH CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411060446.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-05
Publication Date
2024-12-03
Estimated Expiration
2044-08-05

AI Technical Summary

Technical Problem

When the truck passes through, the weight measurement device at the existing highway entrance is susceptible to the driver's pound jump operation, resulting in inaccurate weight measurement and ineffective management of the actual weight of the vehicle.

Method used

By obtaining the vehicle's driving speed and images, using the preset up and down and jumping pound judgment model to determine whether the vehicle has up and down or jumping pounds, and controlling the warning device to issue a warning to ensure that weight measurement is performed when the vehicle is stable, and at the same time, it is estimated by loading images Comparing the weight of the cargo to the actual weight, issuing a weight abnormality warning for enhanced management.

Benefits of technology

It improves the accuracy of vehicle weight measurement, enhances the management of vehicles entering the highway, promptly detects abnormal cargo or falls, and reduces traffic accidents.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118587904B_ABST
    Figure CN118587904B_ABST
Patent Text Reader

Abstract

The present invention relates to a vehicle-road collaboration method, system, terminal and storage medium, and relates to the field of vehicle management, which includes: obtaining the driving speed of the vehicle; when the driving speed falls into a preset measurement speed interval, obtaining the vehicle image of the vehicle; judging whether the vehicle has fluctuated from a preset fluctuation recognition model according to the vehicle image; when the vehicle has fluctuated, judging whether the vehicle has jumped from a preset weight jump judgment model according to the vehicle image; when the vehicle has jumped, controlling a preset warning device to issue a weight jump warning; based on the situation that the vehicle has not fluctuated, controlling a preset weight measurement device to obtain the vehicle weight of the vehicle. The present application has the effect of enhancing the management of vehicles entering the expressway and improving the accuracy of vehicle weight measurement.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of vehicle management, and in particular to a vehicle-road collaboration method, system, terminal and storage medium. Background Art

[0002] Vehicle-road collaboration refers to a road traffic system in which vehicles exchange and share information with other vehicles, pedestrians, road infrastructure, and networks to achieve all-round dynamic and real-time information interaction.

[0003] In the prior art, the entrance toll stations of highways generally adopt vehicle-road cooperative technology. The toll stations generally need to charge according to the weight of the vehicle. A weight measuring device for weighing is generally installed in front of the entrance of the highway. The total weight of the vehicle is measured by the weight measuring device, and the toll station then calculates the highway toll of the vehicle based on the total weight of the vehicle.

[0004] When a truck passes through a weight measuring device, the driver may easily use the scale jump operation to lower the total weight of the vehicle measured by the weight measuring device, resulting in the highway toll not matching the actual weight of the vehicle. Summary of the invention

[0005] In order to enhance the management of vehicles entering the expressway and improve the accuracy of vehicle weight measurement, the present invention provides a vehicle-road collaboration method, system, terminal and storage medium.

[0006] In a first aspect, the present invention provides a vehicle-road collaboration method, which adopts the following technical solution:

[0007] A vehicle-road collaboration method, comprising:

[0008] Get the vehicle's speed;

[0009] When the driving speed falls into a preset measurement speed interval, acquiring a vehicle image of the vehicle;

[0010] Judging whether the vehicle is bumping or not from a preset bump recognition model according to the vehicle image;

[0011] When the vehicle rises and falls, whether the vehicle has jumped is determined from the preset jumping scale judgment model according to the vehicle image;

[0012] When the vehicle weighs a certain amount, the preset warning device is controlled to issue a weighing warning;

[0013] Based on the situation that the vehicle does not rise and fall, a preset weight measuring device is controlled to obtain the vehicle weight of the vehicle.

[0014] By adopting the above technical solution, the driving status of the vehicle on the weight measuring device can be judged by the vehicle image, so that the staff can be warned through the warning device when the vehicle jumps the scale, thereby improving the accuracy of vehicle weight measurement and enhancing the management of vehicles entering the highway.

[0015] Optionally, a loading detection method is also included, and the loading detection method includes:

[0016] Acquire a loading image according to a preset loading image acquisition method;

[0017] Matching the cargo weight from a preset cargo weight matching model according to the vehicle image and the loading image;

[0018] Matching an estimated weight from a preset estimated weight matching model according to the vehicle image and the cargo weight;

[0019] The difference between the estimated weight and the vehicle weight is calculated and defined as the weight difference;

[0020] When the weight difference exceeds a preset error range, a preset warning device is controlled to issue a weight abnormality warning.

[0021] By adopting the above technical solution, the weight of the vehicle is estimated through the loading image and the estimated weight is compared with the actual vehicle weight. When the difference between the two is large, it means that the cargo carried by the vehicle is abnormal and further inspection of the cargo is required, thereby enhancing the management of vehicles entering the highway.

[0022] Optionally, the loading image acquisition method includes:

[0023] Identify the vehicle type from a preset vehicle type recognition model according to the vehicle image, wherein the vehicle type includes an open type and a blocked type;

[0024] When the vehicle type is open, the vehicle image is defined as a loading image;

[0025] When the vehicle type is an obstructed type, the detection position is identified from a preset detection position identification model according to the vehicle image;

[0026] Matching a detection stroke from a preset detection stroke matching model according to the detection position;

[0027] According to the detection stroke, a preset probe camera is controlled to extend into the shielded vehicle and obtain a loading image.

[0028] By adopting the above technical solution, when the vehicle is an open truck, the cargo carried by the vehicle can be observed through the vehicle image. When the vehicle is a covered truck, the probe camera is extended into the vehicle to obtain the image of the cargo carried, thereby obtaining the situation of the cargo carried by the vehicle.

[0029] Optionally, the vehicle type further includes a closed type, and the loading image acquisition method includes:

[0030] When the vehicle type is closed, the blocked position is matched from a preset blocked position matching model according to the vehicle image;

[0031] Matching a blocked trip from a preset blocked trip matching model according to the blocked position;

[0032] Controlling a preset moving device to move to the position of a cargo compartment lock of a closed vehicle according to the blocking stroke, and acquiring a blocking image of the cargo compartment lock;

[0033] Matching the unlocking steps from a preset unlocking means matching model according to the blocking image;

[0034] According to the unlocking steps, the unlocking device preset on the mobile device is controlled to unlock the cargo hold lock and open the cargo hold door, and obtain the loading image in the cargo hold;

[0035] According to the unlocking steps, the unlocking device preset on the mobile device is controlled to close the cargo compartment door and the cargo compartment lock, and the blocking stroke controls the preset mobile device to return to the original position.

[0036] By adopting the above technical solution, when the vehicle is a closed truck, the unlocking device selects a suitable means according to the style of the cargo hold lock to open the cargo hold door to obtain the image of the cargo, and the cargo hold door is closed again after the image is obtained.

[0037] Optionally, a fall detection method is also included, and the fall detection method includes:

[0038] Acquire a driving image of a vehicle traveling on a highway;

[0039] Matching the vehicle number from a preset vehicle number recognition model according to the driving image;

[0040] Matching a comparison image from a preset vehicle image database according to the vehicle number;

[0041] Judging whether cargo falling occurs from a preset cargo falling judgment model according to the driving image and the comparison image;

[0042] When cargo falls, the preset warning device is controlled to issue a cargo falling warning.

[0043] By adopting the above technical solution, by comparing the photos of the vehicle when it is driving on the highway and the photos of the vehicle when it enters the highway, it is determined whether the cargo on the vehicle has fallen or been lost. When the cargo has fallen or been lost, the warning device is used to alert the staff to deal with the vehicle and its fallen cargo in a timely manner.

[0044] Optionally, the fall detection method further includes:

[0045] When cargo falls, the driving position is matched from a preset driving position matching model according to the driving image;

[0046] Matching the entrance and exit locations from a preset entrance location database according to the vehicle number;

[0047] Matching a driving route from a preset driving route matching model according to the entrance position and the driving position;

[0048] Matching the detection position from a preset detection position matching model according to the driving position and the driving route;

[0049] Matching the falling area from a preset falling area matching model according to the detection position and the driving position;

[0050] Control the warning device preset in the falling area to issue a deceleration warning.

[0051] By adopting the above technical solution, when cargo falls and is lost, the approximate area where the cargo falls and is lost can be inferred, and vehicles traveling in the area where the cargo falls and is lost can be reminded to slow down through a notice device, thereby reducing the occurrence of traffic accidents.

[0052] Optionally, a method for handling fallen cargo is also included, and the method for handling fallen cargo includes:

[0053] Matching a detection path from a preset detection path matching model according to the falling area;

[0054] Control the preset drone to fly along the detection path and obtain the road surface image of the falling area;

[0055] Determine whether there is cargo on the road surface from a preset cargo recognition model based on the road surface image;

[0056] When there is cargo on the road, the cargo position is matched from a preset cargo position matching model according to the road image;

[0057] Controlling the preset warning device to display the location where the cargo has fallen according to the cargo position, and matching the warning area from the preset warning area matching model according to the cargo position;

[0058] The notifying device preset in the falling area is controlled to stop issuing a deceleration warning, and the notifying device preset in the warning area is controlled to issue a deceleration warning.

[0059] Based on the fact that there is no cargo on the road surface, a warning device preset in the falling area is controlled to stop issuing a deceleration warning.

[0060] By adopting the above technical solution, the exact falling location of the goods can be further confirmed by drones, making it easier for staff to recover the goods and narrowing the area where the deceleration warning is issued to reduce the impact on vehicle traffic.

[0061] In a second aspect, the present application provides a vehicle-road cooperative system, which adopts the following technical solution:

[0062] A vehicle-road cooperative system, comprising:

[0063] An acquisition module, used for acquiring driving speed, vehicle image, vehicle weight, loading image, blocking image, driving image and road surface image;

[0064] A memory for storing a program of any one of the control methods of the vehicle-road cooperative method;

[0065] The program in the processor and the memory can be loaded and executed by the processor to implement any control method of a vehicle-road cooperative method.

[0066] In a third aspect, the present application provides a computer storage medium capable of storing corresponding programs, which is convenient for implementing a vehicle-road collaboration method and adopts the following technical solution:

[0067] A computer-readable storage medium stores a computer program that can be loaded by a processor and execute any of the above-mentioned vehicle-road cooperative methods.

[0068] In a fourth aspect, the present application provides an intelligent terminal, which adopts the following technical solution:

[0069] An intelligent terminal includes a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute any vehicle-road cooperative method.

[0070] In summary, the present application includes at least one of the following beneficial technical effects:

[0071] 1. The vehicle's driving status on the weight measuring device can be determined through the vehicle image, so that the staff can be alerted through the warning device when the vehicle jumps the scale, thereby improving the accuracy of vehicle weight measurement and enhancing the management of vehicles entering the highway;

[0072] 2. Estimate the weight of the vehicle through the loading image and compare the estimated weight with the actual vehicle weight. If the difference between the two is large, it means that the cargo carried by the vehicle is abnormal and needs further inspection, thereby enhancing the management of vehicles entering the highway;

[0073] 3. By comparing the photos of the vehicle when it is driving on the highway and the photos of the vehicle when it enters the highway, it is determined whether there is any cargo on the vehicle that has fallen or been lost. If cargo has fallen or been lost, the warning device will be used to alert the staff to promptly handle the vehicle and its fallen cargo. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 The present invention is a flow chart of a vehicle-road cooperative method.

[0075] Figure 2 is a flow chart of the loading detection method.

[0076] Figure 3 Is the process of loading the image acquisition method Figure 1 .

[0077] Figure 4 Is the process of loading the image acquisition method Figure 2 .

[0078] Figure 5 The process of fall detection method Figure 1 .

[0079] Figure 6 The process of fall detection method Figure 2 .

[0080] Figure 7 It is a flow chart of the method for handling fallen cargo. DETAILED DESCRIPTION

[0081] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the following Figure 1-7 It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0082] Reference Figure 1 The embodiment of the present application discloses a vehicle-road collaboration method, comprising the following steps:

[0083] Step 100: Obtain the vehicle's driving speed.

[0084] The weight measuring device refers to a device installed at the entrance of the expressway to measure the weight of the vehicle. The weight measuring device generally uses a weighing scale and other equipment. The weight measuring device is selected by the staff according to the actual situation and will not be described in detail here. The driving speed refers to the speed at which the vehicle travels on the weight measuring device. The driving speed can be obtained by a speedometer. The method of obtaining the driving speed is selected by the staff according to the actual situation and will not be described in detail here.

[0085] Step 101: When the driving speed falls into a preset measurement speed interval, a vehicle image of the vehicle is acquired.

[0086] The measurement speed range refers to the pre-set driving speed range of the vehicle on the weight measuring device. When the driving speed exceeds the measurement speed range, it is easy to cause the measured weight to be too large. The measurement speed range is selected by the staff according to the actual situation, and it will not be elaborated here. If the driving speed falls into the measurement speed range, it means that the driving speed meets the measurement specifications.

[0087] The vehicle image refers to a picture of the vehicle driving into the weight measuring device. The vehicle image can be obtained through a camera. The method for obtaining the vehicle image is selected by the staff according to the actual situation and will not be elaborated here.

[0088] Step 102: Determine whether the vehicle is bumping based on the vehicle image using a preset bump recognition model.

[0089] The undulation recognition model refers to a neural network model obtained through sample training in advance. The undulation recognition model can recognize from the picture whether the vehicle has undulations.

[0090] Step 103: When the vehicle rises and falls, whether the vehicle has jumped is determined from a preset jumping weight determination model according to the vehicle image.

[0091] The vehicle's ups and downs mean that the weight measured by the weight measuring device is likely to be inaccurate. Jumping the scale is a weighing technique in which the driver precisely controls the vehicle's clutch, accelerator and brake system to make the tires generate an acceleration when passing through the scale platform, using the inertia principle to change the force on the scale platform to reduce the axle weight.

[0092] The scale jump judgment model refers to a neural network model obtained through sample training in advance. The scale jump judgment model can judge whether the vehicle rises and falls on the weight measuring device, that is, whether the vehicle jumps on the scale, from the ups and downs of the vehicle shown in the vehicle image and the positional relationship between the vehicle and the weight measuring device.

[0093] Step 104: When the vehicle weighs a certain weight, a preset warning device is controlled to issue a weighing warning.

[0094] Warning devices refer to devices used to warn highway workers. Warning devices generally warn workers through screen displays and sound reminders. Warning devices are selected by workers based on actual conditions and are not described here. If a vehicle jumps on the scale, it means that the weight measured by the weight measuring device does not match the actual weight. The jump warning is to remind workers through the warning device that the vehicle jumps on the scale and needs to re-check the weight.

[0095] Step 105: Based on the situation that the vehicle does not rise and fall, control a preset weight measurement device to obtain the vehicle weight of the vehicle.

[0096] If the vehicle does not rise and fall, it means that the weight measured by the weight measuring device at this time is consistent with the actual situation. The weight of the vehicle can be obtained through the weight measuring device, and the weight of the vehicle is the weight measured by the weight measuring device.

[0097] Reference Figure 2 , the loading detection method comprises the following steps:

[0098] Step 200: Acquire a loading image according to a preset loading image acquisition method.

[0099] The loading image refers to a picture of the cargo carried by the vehicle, and the loading image is used to show the cargo carried by the vehicle. The loading image acquisition method is a method for acquiring the loading image.

[0100] Step 201: Match the cargo weight from a preset cargo weight matching model according to the vehicle image and the loading image.

[0101] The cargo weight matching model refers to a neural network model obtained in advance through sample training. The cargo weight matching model can match the cargo weight of the cargo carried by the vehicle from the vehicle size shown in the vehicle image and the cargo situation shown in the loading image.

[0102] Step 202: Match the estimated weight from a preset estimated weight matching model according to the vehicle image and the cargo weight.

[0103] The estimated weight matching model refers to a neural network model obtained through sample training in advance. The estimated weight matching model can match the weight of the vehicle from the vehicle image and add the weight of the cargo to obtain the estimated weight of the vehicle.

[0104] Step 203: Calculate the difference between the estimated weight and the vehicle weight and define it as the weight difference.

[0105] Weight differential is the difference between the estimated weight and the actual weight of the vehicle.

[0106] Step 204: When the weight difference exceeds a preset error range, a preset warning device is controlled to issue a weight abnormality warning.

[0107] The error range refers to the weight difference range that can occur. The error range is selected by the staff according to the actual situation and will not be elaborated here. If the weight difference exceeds the error range, it means that there is an abnormality in the cargo or vehicle, and the staff needs to conduct further inspection. The abnormal weight warning is to remind the staff through the warning device that the vehicle needs to be inspected.

[0108] Reference Figure 3 , the loading image acquisition method comprises the following steps:

[0109] Step 300: Identify the vehicle type from a preset vehicle type recognition model according to the vehicle image, where the vehicle type includes open type and blocked type.

[0110] Vehicle type refers to the style of the vehicle, which includes open, covered and closed types. An open vehicle refers to a vehicle whose cargo can be observed from the outside; a covered vehicle refers to an open vehicle whose cargo is covered by objects such as cloth; and a closed vehicle refers to a vehicle whose cargo is in a closed cargo hold and cannot be observed from the outside.

[0111] The vehicle type recognition model refers to a neural network model obtained through sample training in advance. The vehicle type recognition model can recognize the vehicle type of the vehicle from the vehicle image.

[0112] Step 301: When the vehicle type is open, define the vehicle image as a loading image.

[0113] The vehicle type is open, which means that the cargo carried by the vehicle can be observed through the vehicle image, and the vehicle image can be directly used as the loading image.

[0114] Step 302: When the vehicle type is an obstructed type, a detection position is identified from a preset detection position identification model according to the vehicle image.

[0115] The probe camera refers to a miniature camera that is inserted into a shielded vehicle to obtain loading images. The probe camera is selected by the staff according to the actual situation, so it is not described here. The vehicle type is shielded, which means that the cargo carried by the vehicle cannot be fully observed from the outside, and the probe camera is needed to further obtain the loading image.

[0116] The detection position recognition model refers to a neural network model obtained in advance through sample training. The detection position recognition model can identify from the vehicle image a detection position suitable for a probe camera to extend into to obtain a loading image, wherein being suitable for the probe camera to extend into means that there is space for the probe camera to extend into.

[0117] Step 303: matching the detection stroke from a preset detection stroke matching model according to the detection position.

[0118] The detection stroke matching model refers to a neural network model obtained through sample training in advance. The detection stroke matching model can match the detection stroke of the probe camera moving from the standby area to the detection position and extending into the detection position, and then returning from the detection position to the standby area. The standby area refers to the area where the probe camera is on standby. The standby area is selected by the staff based on actual conditions and will not be elaborated here.

[0119] Step 304: Control a preset probe camera to extend into the shielded vehicle according to the detection stroke and obtain a loading image.

[0120] The loading image of the cargo carried by the obstructed vehicle is obtained through the probe camera, thereby reducing the situation where the loading picture cannot show the cargo carried by the obstructed vehicle.

[0121] Reference Figure 4 , the loading image acquisition method also includes the following steps:

[0122] Step 305: When the vehicle type is closed, a blocked position is matched from a preset blocked position matching model according to the vehicle image.

[0123] The closed vehicle type means that it is necessary to enter the cargo hold of the vehicle to obtain the loading image. The blocking position matching model refers to a neural network model obtained through sample training in advance. The blocking position matching model can match the blocking position of the cargo hold lock of the vehicle from the vehicle image.

[0124] Step 306: Match a blocked trip from a preset blocked trip matching model according to the blocked position.

[0125] The mobile device refers to a device used for movement. The mobile device is provided with a camera for acquiring loading images. The mobile device is selected by the staff according to the actual situation and will not be described in detail here. The blocked trip matching model refers to a neural network model obtained through sample training in advance. The blocked trip matching model can match the blocked trip of the mobile device from the stop area to the blocked position, where the stop area refers to the location where the mobile device is on standby. The stop area is selected by the staff according to the actual situation and will not be described in detail here.

[0126] Step 307: Control a preset moving device to move to the position of a cargo compartment lock of a closed vehicle according to the blocking stroke, and obtain a blocking image of the cargo compartment lock.

[0127] The blocking image refers to the picture of the cargo hold lock. After the mobile device moves to the cargo hold lock according to the blocking itinerary, the blocking image is obtained through the camera set on the mobile device. The method of obtaining the blocking image is selected by the staff according to the actual situation and will not be elaborated here.

[0128] Step 308: Match the unlocking steps from the preset unlocking means matching model according to the blocking image.

[0129] The unlocking means matching model refers to a neural network model obtained through sample training in advance. The unlocking means matching model can match the unlocking steps to open the warehouse lock from the blocked image.

[0130] Step 309: According to the unlocking steps, the unlocking device preset on the mobile device is controlled to unlock the cargo hold lock and the cargo hold door, and obtain the loading image in the cargo hold.

[0131] The unlocking device refers to a device used to open the cargo hold door. The unlocking device may be a mechanical arm. The unlocking device is selected by the staff according to the actual situation and will not be described in detail here. After the cargo hold door is opened, the loading image is obtained through the camera on the mobile device, thereby obtaining the situation of the cargo carried by the closed vehicle.

[0132] Step 310: According to the unlocking steps, the unlocking device preset on the mobile device is controlled to close the cargo door and the cargo lock, and the locking stroke controls the preset mobile device to return to the original position.

[0133] After acquiring the loading image, the cargo hold door is closed through the unlocking device and the mobile device is controlled to return to the parking area, thereby facilitating the control of the next inspection of the mobile device.

[0134] Reference Figure 5 , the fall detection method comprises the following steps:

[0135] Step 400: Acquire a driving image of a vehicle driving on a highway.

[0136] Driving images refer to pictures of vehicles traveling on highways. Driving images can be obtained through driving cameras installed on highways. The method for obtaining driving images is selected by staff based on actual conditions and will not be elaborated here.

[0137] Step 401: Match the vehicle number from a preset vehicle number recognition model according to the driving image.

[0138] The vehicle number refers to the number that is artificially numbered for the vehicle in advance. The vehicle number corresponds to the vehicle one by one. Generally, the vehicle license plate number is directly used as the vehicle number. The vehicle number is selected by the staff according to the actual situation, which will not be elaborated here. The vehicle number recognition model refers to the neural network model obtained through sample training in advance. The vehicle number recognition model can recognize the vehicle number on the vehicle from the driving image.

[0139] Step 402: Match a comparison image from a preset vehicle image database according to the vehicle number.

[0140] The vehicle image database refers to a pre-set database, which records vehicle numbers and their corresponding vehicle images. The comparison image is a vehicle image matched from the vehicle image database by the vehicle number.

[0141] Step 403: judging whether cargo falling occurs from a preset cargo falling judgment model according to the driving image and the comparison image.

[0142] The cargo falling judgment model refers to a neural network model obtained through sample training in advance. The cargo falling judgment model can compare the driving image and the comparison image to judge whether there is cargo falling.

[0143] Step 404: When cargo falls, a preset warning device is controlled to issue a cargo falling warning.

[0144] The warning device reminds the staff that there is a situation of falling cargo, so that the staff can notify the owner of the vehicle in time according to the vehicle number to reduce the situation of further falling cargo causing traffic accidents.

[0145] Reference Figure 6 , the fall detection method further comprises the following steps:

[0146] Step 405: When cargo falls, the driving position is matched from a preset driving position matching model according to the driving image.

[0147] The driving position matching model refers to a neural network model obtained through sample training in advance. The driving position matching model can match the driving position of the vehicle from the driving image.

[0148] Step 406: Match the entrance and exit locations from a preset entrance location database according to the vehicle number.

[0149] The entrance position database refers to a pre-set database, in which the vehicle number and the entrance position of the vehicle corresponding to the vehicle number entering the expressway are recorded.

[0150] Step 407: Match the driving route from a preset driving route matching model according to the entrance position and the driving position.

[0151] The driving route matching model refers to a neural network model obtained through sample training in advance. The driving route matching model can match the driving route that the vehicle takes from the entrance position to the driving position.

[0152] Step 408: Match the detection position from a preset detection position matching model according to the driving position and the driving route.

[0153] Driving cameras are usually evenly set up on highways. Whenever a vehicle passes by a driving camera, the camera will capture a driving image. The detection position matching model refers to a neural network model obtained through sample training in advance. The detection position matching model can match the detection position of the most recent driving image captured before the vehicle arrives at the driving position from the driving route.

[0154] Step 409: Match the falling area from a preset falling area matching model according to the detection position and the driving position.

[0155] The fall area matching model refers to a neural network model obtained through sample training in advance. The fall area matching model can match the fall area from the detection position to the driving position. Every time the vehicle passes the driving camera, the driving camera will obtain a driving image. If cargo is found to have fallen when the vehicle is in the driving position, it means that the cargo should fall when the vehicle is between the driving position and the detection position.

[0156] Step 410: Control a notification device preset in the falling area to issue a deceleration warning.

[0157] When cargo falls on a highway, vehicles traveling at high speeds may not be able to avoid the cargo in time, which may lead to traffic accidents. By notifying vehicles traveling in the falling area to slow down through the notice device, vehicles can respond to the road environment in time, thereby reducing the occurrence of traffic accidents.

[0158] Reference Figure 7 , the cargo falling handling method includes the following steps:

[0159] Step 500: Match a detection path from a preset detection path matching model according to the falling area.

[0160] The detection path matching model refers to a neural network model obtained in advance through sample training. The detection path matching model can match the detection path for checking the road environment of the falling area to determine the location of the fallen cargo.

[0161] Step 501: Control a preset UAV to fly along a detection path and obtain a road surface image of the falling area.

[0162] The drone refers to a device used to obtain the road conditions of the falling area according to the detection path to determine the location of the cargo falling. The drone is selected by the staff according to the actual situation and will not be described in detail here. The road surface image refers to the picture of the road surface in the falling area. The road surface image can be obtained by the camera set on the drone. The method of obtaining the road surface image is selected by the staff according to the actual situation and will not be described in detail here.

[0163] Step 502: Determine whether there is cargo on the road surface from a preset cargo identification model according to the road surface image.

[0164] The cargo recognition model refers to a neural network model obtained in advance through sample training. The cargo recognition model can determine whether there is fallen cargo on the road surface from the road surface image.

[0165] Step 503: When there is cargo on the road surface, the cargo position is matched from a preset cargo position matching model according to the road surface image.

[0166] The cargo location matching model refers to a neural network model obtained in advance through sample training. The cargo location matching model can match the cargo location of the cargo from the road surface image.

[0167] Step 504: Control a preset warning device to display the location where the cargo has fallen according to the cargo location, and match a warning area from a preset warning area matching model according to the cargo location.

[0168] The warning device informs the staff of the location of the goods, so that the staff can recover the goods in time and further handle the goods and the vehicle that lost the goods. The warning area matching model refers to a neural network model obtained through sample training in advance. The warning area matching model can match the area around the location of the goods where the vehicle needs to slow down. By reducing the speed of the vehicle, it can reduce the collision between the vehicle and the goods and cause traffic accidents, and facilitate the subsequent recovery of the goods.

[0169] Step 505: Control the notification device preset in the falling area to stop issuing a deceleration warning, and control the notification device preset in the warning area to issue a deceleration warning.

[0170] The deceleration warning area is narrowed from the falling area from the detection position to the driving position to the warning area centered on the cargo position, thereby reducing the impact on vehicle traffic on the highway.

[0171] Step 506: Based on the fact that there is no cargo on the road surface, control the notification device preset in the falling area to stop issuing a deceleration warning.

[0172] When the drone searches the falling area and does not find any cargo, it is determined that no cargo has fallen. At this time, the deceleration warning can be stopped to reduce the impact on the traffic of vehicles on the highway, and the vehicle driver can be reminded that there is a risk of cargo falling on the vehicle and the cargo on the vehicle needs to be reinforced.

[0173] Based on the same inventive concept, an embodiment of the present invention provides a vehicle-road cooperative system, including:

[0174] The acquisition module is used to acquire driving speed, vehicle image, vehicle weight, loading image, blocking image, driving image and road surface image.

[0175] A memory for storing a program of a control method of any one of the vehicle-road cooperative methods.

[0176] The program in the processor and the memory can be loaded and executed by the processor to implement any control method of a vehicle-road cooperative method.

[0177] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0178] An embodiment of the present invention provides a computer-readable storage medium storing a computer program that can be loaded by a processor and execute a vehicle-road collaboration method.

[0179] Computer storage media include, for example, USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks, and other media that can store program codes.

[0180] Based on the same inventive concept, an embodiment of the present invention provides an intelligent terminal, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute a vehicle-road collaborative method.

[0181] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0182] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A vehicle-road collaboration method, characterized in that: include: Get the vehicle's speed; When the driving speed falls into a preset measurement speed interval, acquiring a vehicle image of the vehicle; Judging whether the vehicle is bumping or not from a preset bump recognition model according to the vehicle image; When the vehicle rises and falls, whether the vehicle has jumped is determined from the preset jumping scale judgment model according to the vehicle image; When the vehicle weighs a certain amount, the preset warning device is controlled to issue a weighing warning; Based on the situation that the vehicle does not rise and fall, controlling a preset weight measuring device to obtain the vehicle weight of the vehicle; It also includes a loading image acquisition method, the loading image acquisition method comprising: Identify the vehicle type from a preset vehicle type recognition model according to the vehicle image, wherein the vehicle type includes open, blocked and closed types; When the vehicle type is open, the vehicle image is defined as a loading image; When the vehicle type is an obstructed type, the detection position is identified from a preset detection position identification model according to the vehicle image; Matching a detection stroke from a preset detection stroke matching model according to the detection position; Control a preset probe camera to extend into the shielded vehicle according to the detection stroke and obtain a loading image; When the vehicle type is closed, the blocked position is matched from a preset blocked position matching model according to the vehicle image; Matching a blocked trip from a preset blocked trip matching model according to the blocked position; Controlling a preset moving device to move to the position of a cargo compartment lock of a closed vehicle according to the blocking stroke, and acquiring a blocking image of the cargo compartment lock; Matching the unlocking steps from a preset unlocking means matching model according to the blocking image; According to the unlocking steps, the unlocking device preset on the mobile device is controlled to unlock the cargo hold lock and open the cargo hold door, and obtain the loading image in the cargo hold; According to the unlocking steps, the unlocking device preset on the mobile device is controlled to close the cargo door and the cargo lock, and the locking stroke controls the preset mobile device to return to the original position; Also included is a fall detection method, the fall detection method comprising: Acquire a driving image of a vehicle traveling on a highway; Matching the vehicle number from a preset vehicle number recognition model according to the driving image; Matching a comparison image from a preset vehicle image database according to the vehicle number; Judging whether cargo falling occurs from a preset cargo falling judgment model according to the driving image and the comparison image; When cargo falls, the preset warning device is controlled to issue a cargo falling warning, and the driving position is matched from a preset driving position matching model according to the driving image; Matching the entrance and exit locations from a preset entrance location database according to the vehicle number; Matching a driving route from a preset driving route matching model according to the entrance position and the driving position; Matching the detection position from a preset detection position matching model according to the driving position and the driving route; Matching the falling area from a preset falling area matching model according to the detection position and the driving position; Controlling a warning device preset in the falling area to issue a deceleration warning; Also included is a cargo falling processing method, the cargo falling processing method comprising: Matching a detection path from a preset detection path matching model according to the falling area; Control the preset drone to fly along the detection path and obtain the road surface image of the falling area; Determine whether there is cargo on the road surface from a preset cargo recognition model based on the road surface image; When there is cargo on the road, the cargo position is matched from a preset cargo position matching model according to the road image; Controlling the preset warning device to display the location of the fallen cargo according to the cargo position, and matching the warning area from the preset warning area matching model according to the cargo position; Controlling the notification device preset in the falling area to stop issuing a deceleration warning, and controlling the notification device preset in the warning area to issue a deceleration warning; Based on the fact that there is no cargo on the road surface, a warning device preset in the falling area is controlled to stop issuing a deceleration warning.

2. A vehicle-road collaboration method according to claim 1, characterized in that: Also included is a loading detection method, the loading detection method comprising: Acquire a loading image according to a preset loading image acquisition method; Matching the cargo weight from a preset cargo weight matching model according to the vehicle image and the loading image; Matching an estimated weight from a preset estimated weight matching model according to the vehicle image and the cargo weight; The difference between the estimated weight and the vehicle weight is calculated and defined as the weight difference; When the weight difference exceeds a preset error range, a preset warning device is controlled to issue a weight abnormality warning.

3. A vehicle-road cooperative system, characterized in that: include: An acquisition module, used for acquiring driving speed, vehicle image, vehicle weight, loading image, blocking image, driving image and road surface image; A memory, used to store a program of a control method of a vehicle-road cooperative method as claimed in any one of claims 1 to 2; The program in the processor memory can be loaded and executed by the processor to implement the control method of the vehicle-road cooperative method as described in any one of claims 1 to 2.

4. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the vehicle-road cooperative method as claimed in any one of claims 1 to 2.

5. An intelligent terminal, characterized in that: It comprises a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute the vehicle-road cooperative method as described in any one of claims 1 to 2.

Citation Information

Patent Citations

  • Vehicle overload dynamic monitoring system and working method of vehicle overload dynamic monitoring system

    CN104574969A

  • Road surface detection method and device, electronic equipment and storage medium

    CN112528710A